A smartphone is a personal device that can always be with someone. Smartphones and related mobile devices are evolving into a form of personal assistant. It will be natural to converse with this assistant by voice, particularly considering the limitations of typing on the small devices. This talk notes the key features of such a voice-enabled assistant, the hurdles in achieving the vision fully, and possible approaches to overcoming those hurdles.

In a world rapidly filling up with smartphones that have information-rich user interfaces, what role does speech play? In the future, will access to customer service be mediated through mobile apps and will this make the traditional speech and IVR redundant? Will speech simply be a keyboard replacement or should we expect novel new paradigms? This talk explores these issues.

Social media has become a critical channel for organizations. However, organizations need strategies and technologies to effectively scale and integrate social media for a holistic approach to customer service. Organizations can now have meaningful interactions through social media channels in the same agent desktop where agents interact with callers. This presentation provides insight into combining two distinct functions to bring social monitoring and social interaction into the overall contact center and customer service strategies.

The potential for enabling immediate customer engagement is attracting companies to social media sites, but most organizations fail to harness the full value of these connections in the contact center. This talk shows how to apply business rules to social interactions to enhance agent efficiency, integrate social media into existing processes, and develop key metrics. How to cut through the social noise, identify which posts are most critical to your company, and present best practices to align social media tools with the contact center are discussed.

When upgrading IVR systems, many organizations request “like for like” replacement of the functionality they first implemented many years ago without considering whether it is still appropriate or effective for today’s call center.  This talk makes the case for spending time before a replacement project to validate the functionality, technology, and customer experience to ensure the long-term success of the project.

Replacing an IVR can seem trivial until you're immersed in the complexities of the project. The migration of an IVR to a new platform introduces challenges that your organization may not have faced in some time. Hear about a large IVR migration currently underway and some of the measures taken to ensure its success.

Customer frustrations are increasing in today’s challenging business climate. Under heavy pressure to improve customer satisfaction, enterprises need to rely on a combination of the right technologies, people, and processes to enhance the customer experience and increase the bottom line. Therefore,
enterprises need to develop a clearer line of sight with the customer and their needs when it comes to communication. This talk reports key findings from Ovum’s latest survey of 4,000 consumers on customer service preferences for client engagement.

Given advancements in speech recognition, transcription, translation, text-to-speech synthesis, and application processing power, the days of a speech based virtual personal assistant are closer than ever. Yet a number of hurdles remain as solutions providers must overcome gaps in some specific areas, including speaker identification, noise cancellation, speech extraction, language recognition, translation, and, ultimately, understanding. This talk explores these gaps and presents an exposition of the technologies that bridge them.

Most IVR systems require callers to provide certain pieces of information to authenticate before completing their tasks. When the information requested
is not readily available or familiar to the caller, this results in decreased caller satisfaction and unnecessary transfers. Some systems include “I don’t know” options to allow for such cases, but is this necessary or are callers just trying to circumvent the system? This session explores ways to optimize caller satisfaction and retention using strategies from real-world examples.

Targeting designs to the needs, expectations, and contexts of specific user groups is key to maximizing performance and user satisfaction. However, business realities often require us to accommodate several disparate user groups within a single speech application. This talk addresses such design and performance challenges, and offers practical advice based on Tellme deployments spanning several verticals and application types.

Traditional methods for VUI design produce cumbersome documents that confuse the client and obfuscate incremental changes from the developer.
By applying proven concepts from object-oriented design methodologies and off-the-shelf software, VUI designs can become comprehensible to a wider
audience. Because object-oriented designs incorporate principles that the developers are familiar with, the gap between design and development can
be narrowed, leading to reduced confusion, increased delivery ability, and an overall improvement in the quality of the project.

Hear how smart design tools helped Blue Cross & Blue Shield of Rhode Island speed up a complete overhaul of its customer service application from requirements to production. Smart design tools and a smart design accelerated reviews, prompt recording, usability testing, coding, unit testing, and change management.

Sketching is increasingly being used in the interaction design community (and elsewhere) for generating and analyzing ideas, storyboarding, and creating low-fidelity prototypes. But sketching is not usually a technique that comes to mind when designing for voice. This talk shows how sketching can uncover potential problems early in the design and can help the application better fit people and the contexts they’re in. Simple techniques will be demonstrated for sketching and modeling voice interactions.

The use of speech in multimodal applications forces us to ask how to blend design disciplines of those who’ve done little work outside speech and IVR
and those who have worked exclusively in GUI design. This talk focuses on the need for that blend and encourages cross-mode skill training for designers and managers. The overarching goal is to enable designers to create highperformance multimodal applications that are optimized for business success and positive user experiences.

The Caller Experience Index quantifies the subjective caller experience by automatically measuring the frequency of dissatisfying events such as dropped calls, multiple retries, transfers, and verbalized frustration. Drawing on benchmark data Raytheon BBN compiled for several of its Fortune 100 clients, Alwan shows how to generate actionable insights for improving the caller experience.

Contact center and IVR self-service applications play significant roles in customer experience optimization. Optimizing customer experiences increases
customer loyalty, cost savings, and revenue. Deploying a quality management, measurement, and improvement process around new and existing customer-facing apps is an ideal way to meet strategic objectives by improving internal metrics and, most importantly, increasing customer satisfaction.

By creating a cloud-based, on-demand platform with an open API, an ecosystem of developers can create new applications to overlay the current contact center infrastructure, bypassing the IVR experience while connecting to the appropriately skilled agent. Using a multichannel, on-demand platform with robust APIs, a mobility ecosystem of partners, developers, and clients are creating and delivering new mobile and client care applications such as voiceenabling the smartphone application or immediate callback from agents with context and skills.

How can you educate your customers about your new mobile care channel, drive faster adoption, and create a better customer experience? Learn about
strategies for using your IVR to actually drive mobile adoption; how to tie your voice channel to your mobile channel to create a seamless interaction across channels; and options for expanding and personalizing your self-service care options just by knowing you’ve got a mobile caller on the line.

Delivering exceptional customer experiences requires the delivery of up-to-date, contextual, and timely information that is consistent across all customer interaction channels. This information can be used to produce dynamic, personalized, and memorable phone experiences. Integration between the IVR and a knowledge foundation provides the ability to identify, segment, and route each caller appropriately based on the contextual information about the caller’s specific need. This information is also available to the human agent answering the call.

“I don’t want to talk to some computer system” was a common reaction to older IVRs. Today, automation is changing the game, making IVR core to providing the high touch customers demand. See real-world industry examples of how speech self-service can actually drive high touch customer intimacy. Learn the 10 fundamental tenets and the technical infrastructure needed for a solution that uses existing enterprise data. Learn to exceed customer expectations with intelligent customer intimacy.

By using multiple channels of communication, interaction becomes less taxing, audio instructions can be spoken to free up the visual channel, and pictures can be used when a visual is most natural. Speech can be used to respond to queries and instructions while hands are free to carry out the instructions at the very physical site where the user needs to troubleshoot. This presentation reviews the design process, the solution architecture, and demos a working multimodal automated application that interacts with a live IVR.

Where does speech technology fit into smartphone applications? This session presents the current state of smartphone app design, how speech technology will shape better smartphone app design, and takes a look at the future of adding the right amount of speech at the right places. Join us to see how you can take advantage of the GUI-speech gap in smartphone application design.

Kinect eliminates the need for a controller and instead relies on a combination of speech and body gestures to interact with the game. How can these two input modes be combined to enhance one another? How do you deal with the challenges of multiple speakers, background noise, and distance from the microphone? How do you use visual feedback to support error recovery? Gaming is all about having fun. How can we ensure that speech enhances this experience? Attend this session for the answers to these questions.

As home entertainment systems start to offer hundreds of channels and movies on demand, subscribers can no longer practically search for content using program listings. We describe experiments using a voice-activated system that helps users find programs by genre, title, cast names, time/date, etc. Hierarchical statistical language models enable a combination of historical behavior with current popularity ratings to increase recognition accuracy. A demo of a working prototype will show the interaction between the user, the speech recognizer, and the video display.

In commercial spoken dialogue systems, call flows are traditionally built by call flow designers with a predefined business logic. This talk presents a
method for automatically deriving a call flow, minimizing the average number of user turns given a business logic and a frequency distribution of call reasons. As an example, the method was applied to a call routing application whose manually built call flow is processing about 4 million calls per month and whose call reason distribution served to measure the impact of the automatic call flow generation.

When the number of possible caller intents reaches a certain point in applications such as call steering, voice search, and FAQ, few enterprises can afford the required months of utterance analysis, grammar development, and tuning. This session presents an innovative solution to the problem of handling complex caller intents. A dialogue manager automatically generates the call flow from a model of possible intents. Examples discussed  include a large natural language application deployed in the travel industry.